Introduction to Clinical Informatics fills a void in the Computer in Health Care series. With this volume, Patrice Degoulet and Marius Fieschi provide a comprehensive view of medical informatics and carry that concept forward into the realm of clinical informatics. The authors draw upon their experi ences as medical school faculty members in France, where informatics has long been integrated into the curriculum and where the French version of this very book has been used, tested, and revised. In intent and content, this volume stands as the companion volume to Introduction to Nursing Informatics, one of the series' best selling titles. For practitioners and students of medicine, pharmacy, and other health profes sions, Introduction to Clinical Informatics offers an essential understanding how computing can support patient care, clarifying practical uses and critical issues. Today medical schools in the United States are making informatics a part of their curriculum, with required medical informatics blocks at the onset of training serving as the base for problem-based learning throughout the course of study. In an increasingly networked and computerized environ ment, health-care providers are having to alter how they practice. Whether in the office, the clinic, or the hospital, health-care professionals have access to a growing array of capabilities and tools as they deliver care. Learning to use these becomes a top priority, and this volume becomes a valuable resource."

This book contains 26 papers describing research in the do- main of Artificial Intelligence in Medicine. The papers are grouped around the following themes: Methodology, knowledge representation, clinical applications, modelling, uncertain- ty management, knowledge acquisition, and the user perspec- tive. The book gives an overview of the current state of AI in medicine research in Europe. It presents several techni- ques and methods that are likely to play an important role in future applications. In the section on clinical applica- tions not only existing systems are described, but results of evaluation studies are presented as well.

Introduction to Clinical Informatics fills a void in the Computer in Health Care series. With this volume, Patrice Degoulet and Marius Fieschi provide a comprehensive view of medical informatics and carry that concept forward into the realm of clinical informatics. The authors draw upon their experi ences as medical school faculty members in France, where informatics has long been integrated into the curriculum and where the French version of this very book has been used, tested, and revised. In intent and content, this volume stands as the companion volume to Introduction to Nursing Informatics, one of the series' best selling titles. For practitioners and students of medicine, pharmacy, and other health profes sions, Introduction to Clinical Informatics offers an essential understanding how computing can support patient care, clarifying practical uses and critical issues. Today medical schools in the United States are making informatics a part of their curriculum, with required medical informatics blocks at the onset of training serving as the base for problem-based learning throughout the course of study. In an increasingly networked and computerized environ ment, health-care providers are having to alter how they practice. Whether in the office, the clinic, or the hospital, health-care professionals have access to a growing array of capabilities and tools as they deliver care. Learning to use these becomes a top priority, and this volume becomes a valuable resource.

The current scarcity of expert systems where the reasoning is based on Bayesian probability theory may be due to misconceptions about probabilities found in the literature. As argued by Cheeseman (1985), these misconceptions have led to the attitude: "The Bayesian approach doesn't work - so here is a new scheme." Several of these expert systems based on ad hoc "probability" concepts have been successful in a number of ways, demonstrating the necessity of being able to handle uncertainty in medical expert systems. They also demonstrate the need for a theoretically sound handling of uncertainty. In Andersen et al. (1986) it was postulated that knowledge organized in a causal network can be used for a unified approach to the main tasks of a medical expert system: diagnosis, planning of tests and explanations. The present paper explores this postulate in a causal probabilistic network. It also provides a practical demonstration that the problems supposedly associated with probabilistic networks are either non-existent or that practical solutions can be found. This paper reports on the methods implemented in MUNIN* -an expert system for electromyography (EMG) (Andreassen et al. 1987). EMG is the diagnosis of muscle and nerve diseases through analysis of bioelectrical signals from muscle and nerve tissue. In Andreassen et al.